mlsanityData to 7 Oct 2026

Crowd3D: Towards Hundreds of People Reconstruction from a Single Image

arXiv 2301.09376 ↗First posted 23 Jan 2023cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Image-based multi-person reconstruction in wide-field large scenes is critical for crowd analysis and security alert. However, existing methods cannot deal with large scenes containing hundreds of people, which encounter the challenges of large number of people, large variations in human scale, and complex spatial distribution. In this paper, we propose Crowd3D, the first framework to reconstruct the 3D poses, shapes and locations of hundreds of people with global consistency from a single large-scene image. The core of our approach is to convert the problem of complex crowd localization into pixel localization with the help of our newly defined concept, Human-scene Virtual Interaction Point (HVIP). To reconstruct the crowd with global consistency, we propose a progressive reconstruction network based on HVIP by pre-estimating a scene-level camera and a ground plane. To deal with a large number of persons and various human sizes, we also design an adaptive human-centric cropping scheme. Besides, we contribute a benchmark dataset, LargeCrowd, for crowd reconstruction in a large scene. Experimental results demonstrate the effectiveness of the proposed method. The code and datasets will be made public.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 37 of its 51 references that are in the map. First posted on arXiv 23 Jan 2023.

Builds on

37 of 51 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  5. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  6. 2017End-to-end Recovery of Human Shape and Posecited by 883
  7. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  8. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  9. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
  10. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  11. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  12. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
25 more
  1. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  2. 2021AGORA: Avatars in Geography Optimized for Regression Analysiscited by 203
  3. 2017Single-Shot Multi-Person 3D Pose Estimation From Monocular RGBcited by 195
  4. 2021Putting People in their Place: Monocular Regression of 3D People in Depthcited by 141
  5. 2020Coherent Reconstruction of Multiple Humans from a Single Imagecited by 136
  6. 2021SPEC: Seeing People in the Wild with an Estimated Cameracited by 134
  7. 2019Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Imagecited by 131
  8. 2022Recovering 3D Human Mesh from Monocular Images: A Surveycited by 103
  9. 2018LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Imagescited by 88
  10. 2019Human Mesh Recovery from Monocular Images via a Skeleton-disentangled Representationcited by 87
  11. 2019XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Cameracited by 68
  12. 20203D Human Mesh Regression with Dense Correspondencecited by 66
  13. 2021Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenescited by 64
  14. 2020img2pose: Face Alignment and Detection via 6DoF, Face Pose Estimationcited by 57
  15. 2019TexturePose: Supervising Human Mesh Estimation with Texture Consistencycited by 53
  16. 2020SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimationcited by 52
  17. 2020PANDA: A Gigapixel-level Human-centric Video Datasetcited by 45
  18. 2021Body Meshes as Pointscited by 45
  19. 2020HMOR: Hierarchical Multi-Person Ordinal Relations for Monocular Multi-Person 3D Pose Estimationcited by 44
  20. 2020Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimationcited by 36
  21. 2021PandaNet : Anchor-Based Single-Shot Multi-Person 3D Pose Estimationcited by 22
  22. 2020SMPLy Benchmarking 3D Human Pose Estimation in the Wildcited by 16
  23. 2021Body Size and Depth Disambiguation in Multi-Person Reconstruction from Single Imagescited by 11
  24. 2020Unsupervised Cross-Modal Alignment for Multi-Person 3D Pose Estimationcited by 10
  25. 2021Single View Physical Distance Estimation using Human Posecited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 4; 2026: 5.

12 papers.

  1. 2023Reconstructing Groups of People with Hypergraph Relational Reasoningcited by 18
  2. 2024Closely Interactive Human Reconstruction with Proxemics and Physics-Guided Adaptioncited by 18
  3. 2025WorldPose: A World Cup Dataset for Global 3D Human Pose Estimationcited by 13
  4. 2025Reconstructing Close Human Interaction with Appearance and Proxemics Reasoningcited by 4
  5. 2025DyCrowd: Towards Dynamic Crowd Reconstruction from a Large-scene Videocited by 3
  6. 2024RCR: Robust Crowd Reconstruction with Upright Space from a Single Large-scene Imagecited by 2
  7. 2026JRDB-Pose3D: A Multi-person 3D Human Pose and Shape Estimation Dataset for Roboticscited by 1
  8. 2025ANTHROPOS-V: benchmarking the novel task of Crowd Volume Estimationcited by 0
  9. 2026CrowdGaussian: Reconstructing High-Fidelity 3D Gaussians for Human Crowd from a Single Imagecited by 0
  10. 2026SocialMirror: Reconstructing 3D Human Interaction Behaviors from Monocular Videos with Semantic and Geometric Guidancecited by 0
  11. 2026Contrastive Multi-Modal Hypergraph Reasoning for 3D Crowd Mesh Recoverycited by 0
  12. 2026Crowd4D: Scene-Aware Monocular 4D Crowd Reconstructioncited by 0